How to Use the Sensible MCP in LangChain

Q: How can a LangChain agent decide which Sensible configuration to use?

You can build a chain where the agent first calls classifysync on a document. Based on the returned document type, your agent's logic can then select the appropriate configuration and pass it to extractfromurlwithconfig.

Build intelligent document processing pipelines your LangChain agent can execute step-by-step.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sensible MCP to LangChain

Create your Vinkius account to connect Sensible to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sensible with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Manage Document Configurations in a Chain

This toolset lets your agent manage the entire document parsing lifecycle. It's not about one-off extractions; it's about building a repeatable process. Your agent can `create_document_type` for a new form, `create_configuration` to define its schema, and then `publish_configuration` to a production environment. When a schema drifts, the agent can use `update_configuration` to push a new version. This isn't a black box. Your agent has full control over the rules Sensible uses, which means you can chain these actions together to automate what's usually a manual, tedious job.

Run Asynchronous Extractions

Run complex document analysis without blocking your main thread. Your LangChain agent can kick off a job by getting a signed URL with `generate_upload_url`, then start the process with `extract_from_url`. The agent is free to do other work while Sensible handles the parsing. Later, it can circle back to check the status and get the results using `get_document`. This is perfect for building workflows that handle high-volume uploads. You can even build a chain that classifies a document with `classify_async` first, then routes it to a specific extraction configuration.

Go From Raw PDF to Final Report

Turn raw, unstructured data from PDFs into structured reports automatically. After your agent confirms an extraction is complete, it can call `generate_csv` or `generate_excel` to compile the JSON results into a spreadsheet. This is the last link in the chain. Your agent can take a folder of documents, run them through a classification and extraction pipeline via the Sensible MCP Server, and then deliver a ready-to-use report. The server handles the conversion, so your code doesn't have to.

Setup guide

Set up Sensible MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Sensible tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "sensible-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Sensible transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Sensible. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Sensible now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Sensible MCP in LangChain

You can build a chain where the agent first calls `classify_sync` on a document. Based on the returned document type, your agent's logic can then select the appropriate configuration and pass it to `extract_from_url_with_config`.

Yes. Every tool call made through the LangChain MCP adapter is automatically traced. You'll see the inputs, outputs, and latency for each Sensible operation right inside LangSmith.

For batch jobs, design a chain that iterates through your documents, calls `extract_from_url` for each one, and collects the job IDs. A separate step can then poll `get_document` for all IDs and, once all are complete, call `generate_csv`.

You don't. The Vinkius MCP endpoint handles authentication. You provide your single endpoint token to the `MultiServerMCPClient`, and it manages the underlying Sensible credentials for you.

Sensible processes the content of your PDFs, images, and other documents to extract data. Your documents are handled in an ephemeral environment during processing. Because LangChain calls the MCP Server directly, the data flow is between your agent and the Vinkius-managed server, which helps contain where your sensitive document data travels.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript